Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Language Modeling Downstream Evaluation on Downstream tasks Average (test)

58.02Average Score

BlockPruner

34.6240.69546.7752.845Jun 15, 2024Oct 14, 2024Feb 13, 2025Jun 15, 2025Oct 14, 2025Feb 13, 2026Jun 15, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
58.02
2024.06
57.4
2024.06
57.02
2024.06
56.1
2024.06
53.26
2024.06
52.36
2024.06
50.08
2024.06
49.18
2026.06
48.2
2026.06
47.5
2026.06
47.4
2024.06
46.38
2024.06
45.41
2024.06
44.51
2026.06
44.4
2024.06
43.71
2024.06
42.85
2024.06
42.79
2024.06
41.97
2024.06
41.41
2024.06
39.34
2024.06
38.9
2024.06
37.75
2024.06
37.48
2024.06
36.8
2024.06
36.49
2024.06
35.89
2024.06
35.52